Story
receptron/mulmocast-cli
Create high-quality MulmoScript through structured multi-phase creative process
把中文口播文案做成像素风 + 坐标系隐喻 + 打字机字幕的动画解说视频(含 edge-tts 配音):先问 5 项输入、写分镜表与 3 张关键帧等确认,再写 spec.json、配音、逐帧渲染 1080p mp4。用户给文案并要像素风 / 注意力赌博那种风格、或确认是像素解说系列续集时使用;独立单片和其他风格走 $cs-code-video,暗夜星空知识片走 $cs-knowledge-film。
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cs-pixel-explainer .claude/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .claude/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cs-pixel-explainer .agents/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .agents/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cs-pixel-explainer .cursor/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .cursor/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ChenShuo2004/cs-skills.git --path cs-pixel-explainer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cs-pixel-explainer .gemini/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .gemini/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/cs-pixel-explainer .github/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .github/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-pixel-explainer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cs-pixel-explainer .opencode/skills/cs-pixel-explainer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cs-pixel-explainer" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-pixel-explainer into .opencode/skills/cs-pixel-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-pixel-explainer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cs-pixel-explainer把中文口播文案做成像素风 + 坐标系隐喻 + 打字机字幕的动画解说视频(含 edge-tts 配音):先问 5 项输入、写分镜表与 3 张关键帧等确认,再写 spec.json、配音、逐帧渲染 1080p mp4。用户给文案并要像素风 / 注意力赌博那种风格、或确认是像素解说系列续集时使用;独立单片和其他风格走 $cs-code-video,暗夜星空知识片走 $cs-knowledge-film。
Cs Pixel Explainer is an agent skill from ChenShuo2004/cs-skills. 把中文口播文案做成像素风 + 坐标系隐喻 + 打字机字幕的动画解说视频(含 edge-tts 配音):先问 5 项输入、写分镜表与 3 张关键帧等确认,再写 spec.json、配音、逐帧渲染 1080p mp4。用户给文案并要像素风 / 注意力赌博那种风格、或确认是像素解说系列续集时使用;独立单片和其他风格走 $cs-code-video,暗夜星空知识片走 $cs-knowledge-film。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including assets (for example `agents/openai.yaml`, `assets/example-spec.json` and `engine/tts.py`).
It sits in Media & Creative, covering Text to speech and voice. It works with Playwright. The repository describes itself as: 陈硕的 Codex Skills 与 AI 工作流手册:把产品、内容、调研与交付沉淀为可复用的智能工作流。 The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 6f5009d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (JavaScript, Python and Batch), which the agent can run.
Shell commands in SKILL.md call:
nodepythongitpython3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cs Pixel Explainer loads about 2.2k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 560 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ChenShuo2004/cs-skills at commit 6f5009d, republished under its MIT licence (© ChenShuo2004). 560 words, ~2,214 tokens.
.claude/skills/cs-pixel-explainer/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.<!-- CS Skills · 陈硕 | portable skill entry | https://github.com/ChenShuo2004/cs-skills -->
参考风格:夜晚像素街道 + 左上角「关系坐标」HUD + 打字机字幕 + 把道理抽象成坐标系/老虎机/网络图。
全部画面由代码绘制(Canvas),页面暴露 window.render(t),Playwright 逐帧截图 + FFmpeg 合成 1080p MP4;配音用 edge-tts,每句真实时长驱动整条时间轴,字幕和动画自动对齐配音。
流程总览:问 5 项输入 → 设计隐喻 → 分镜表(等确认)→ 3 张关键帧(等确认)→ 配音 → 逐场景制作自检 → 整片 → 交付。
引擎 = engine/ 目录下 5 个文件:engine.html(场景库)timeline.mjs render.mjs tts.py 配音.bat。
按顺序找,找到一处即可,复制到工作目录 ~/pxe/engine/:
engine/(从 GitHub 安装时就在这里;没有就 git clone https://github.com/ChenShuo2004/cs-skills,目录 cs-pixel-explainer/engine/)claude/pixel-explainer/engine.html 等 → project_read 后写入文件像素纯度参考实现:assets/reference-wizard.html(施法巫师,128×96 调色板索引缓冲、整数倍放大、10 张/秒姿势量化、预分配粒子池、固定步长重放的 render(t)、无缝循环)。新场景、新角色从它的写法起步。
运行依赖:node + playwright、ffmpeg、Noto CJK 字体;Playwright 需有 Chromium 浏览器,若未安装其自带浏览器,渲染脚本会尝试使用本机 Chrome。Claude Cowork 环境若已预装这些依赖,无需重复安装。配音需要 Python、edge-tts 和可访问语音服务的网络;tts.py 缺少 edge-tts 时会自动安装。
配音.bat 缺了就按下面内容重建(必须 CRLF 换行,UTF-8):
@echo off
chcp 65001 >nul
cd /d %~dp0
where python >nul 2>nul && (python tts.py) || (py tts.py)
echo.
echo 配音完成后回到 Claude 说一声「配音好了」即可
pause示例 spec:assets/example-spec.json(10 个场景全覆盖,写新 spec 前先读它)。
原材料里已经能确定的项直接写出来请用户确认,不重复问:
bgm)/ 代码合成芯片配乐 / 无配乐;要不要配音(默认要,男声 zh-CN-YunxiNeural)用户回答「你定」的项才用默认值,并在分镜表顶部标注。无人值守时主题取自文案,其余用默认值,并在报告最前面列出假设。
pixelDissolve 只作兜底,不要每场都用。imageSmoothingEnabled = false,CSS image-rendering: pixelated。createLinearGradient/RadialGradient、shadowBlur、半透明叠色。渐变用色带 + Bayer 4×4 有序抖动;发光用 1 像素轮廓光或几圈抖动像素;闪光、变暗用调色板映射表整体换一级。Uint8Array 索引缓冲再查表写 ImageData。engine.html 的 glow()、shadowBlur、渐变背景、高分辨率叠加文字不符合本标准。动到哪个场景就把哪个场景改到标准,改完同步三处存档。Math.random();随机数带固定种子;帧和帧之间不保存状态。document.fonts.ready)再截图,不然前几帧是默认字体。镜头 [N]|[开始–结束秒](按每字 0.235 秒估)|场景 type
画面:构图、元素、文字(大字/标签/字幕)
动作:进场、主要动作、出场(用哪些 events)
镜头:推 / 拉 / 跟随 / 固定
声音:配乐段落、音效(落在哪个动作上)
转场:怎么从画面内容长到下一场cs-code-video 的 audio.py beats),场景切换和关键动作落在拍点上。发出前对照第 2 节自查。spec.json(第 7 节),放在 ~/pxe/<slug>/spec.json。node engine/timeline.mjs <dir> && node engine/render.mjs <dir> --preview 后挑 3 帧拼图给用户;自己先 Read 检查重叠、出框、文字太小、主体太小,修好再给。engine/tts.py、engine/配音.bat 复制到 <项目目录>/,与 spec.json 放在一起。本机可联网时运行 python3 tts.py;Windows 也可双击 配音.bat。audio/line_000.mp3… 和 audio/DONE。确认 DONE 与句子数一致后,再运行 timeline.mjs,让真实配音时长驱动画面。device_commit_files 将上述文件写到用户已连接的电脑,请用户运行配音,再用 device_stage_files 取回 audio/;不要假定每台电脑的盘符或目录相同。cs-code-video 的 audio.py sfx / music 用 numpy 从零合成(像素风优先方波/三角波芯片音色)。听不到声音,就把混音波形画成图检查,确认没有削顶爆音、意外静音。node engine/timeline.mjs <dir> && node engine/render.mjs <dir> → video.mp4(自带配音)+ subtitles.srt。2 核约 0.5–1× 实时,3 分钟视频约 6–10 分钟,用 timeout 600000,必要时 --from/--to 分段。video.mp4、subtitles.srt 和项目目录的真实路径;在 Claude Cowork 中可再用 SendUserFile 或 device_commit_files 交付给用户。没有配音也能出片:跳过第 6 步,timeline 按每字 0.235s 估算,输出无声版 + SRT。
street 开场:标题大字(sub:false 的第一句念标题)→ 主角从 (0,0) 出发 → 全力投入(run/throw)→ 被拒绝(shield/reject)→ 塌陷(collapse)abyss:掉进深渊,落地,大字点题「敌人 (+100,-100)」;正向结局用 tone:"gold"axes:把故事抽象成坐标系:陌生人在原点、朋友塔在右上、主角在右下,虚线「高 X 消耗」,正/负箭头,原点画圈给反转金句slot:「你只能控制 X,Y 由 N 个变量决定」→ 转两次老虎机card × N:逐个解释变量(waves 同频/不同频,split 两种状态对比,beats 节奏合拍,quotes 越界阈值)network / triangle:给出方法(弱纽带、三元闭包、多点连接)street(friends>0,气泡)收尾 → bigtext 点阵金句[y]黄[/y] 正向、[r]红[/r] 负向/反转、[c]青[/c] [g]绿[/g],每句最多 1–2 处。// 只是说明,真实 JSON 不能写注释){
"title": "视频标题",
"voice": "zh-CN-YunxiNeural", // 男声叙述推荐;也可 zh-CN-YunjianNeural(更沉)/ zh-CN-XiaoxiaoNeural(女)
"rate": "+4%", // 语速
"hud": { "label": "关系坐标", "x": "注意力", "y": "情绪", "top": "友", "bottom": "敌" },
"lineGap": 0.22, "sceneTail": 0.45, // 可选:句间隔 / 场景尾巴(秒)
"bgm": "bgm.mp3", "bgmVolume": 0.12, // 可选:放在项目目录里的背景音乐
"scenes": [ { "type": "...", "lines": [...], "props": {...}, "events": [...], "hud": [...], "showHud": true } ]
}lines:字符串,或 { "text": "带[y]标记[/y]的字幕", "say": "念的内容(默认=去掉标记的 text)", "sub": false, "pause": 0.3 }。
时间锚点 at:所有事件都用「本场景第几句」表示,2 = 第 3 句开始时,2.5 = 第 3 句念到一半,所以配音变长变短动画都跟着走。
hud:[[at, x, y], ...],x∈[0,100],y∈[-100,100];只在 showHud:true 的场景显示(hudFadeIn 秒后淡入)。场景其他通用字段:lead(首句前留白秒)、hold(尾部额外停留)、minDur、transition:"none"。
| type | props | events(do) |
|---|---|---|
street 夜晚街道 | title{line1,line2,until,color} 开场大字;npc{x:330,enterAt:0.3,enter:false,color};crowd(10) 路人数;friends 主角身边朋友数;heroX(150);heroWalk:false | emote{text:"!",who:"hero"/"npc",color}、run{to} 冲向 npc、walk{to}、throw{item:"heart"/"gift"}、shield{label} npc 红色六边形、reject{label,push} 弹开、collapse 地面塌陷坠落(下一场景接 abyss)、bubble{who:"hero"/"npc"/朋友序号,text,dur} |
abyss 深渊 | tone:"red"/"gold",label 大字,sub 小字,landAt(1.6 秒,0=不坠落直接站着) 落地时间,labelAtLine 用行锚点控制大字出现 | – |
axes 坐标系 | xLabel yLabel;points:[{x,y,kind:"people"/"tower"/"hero"/"dot",label,color,at,labelSide:"left"/"right"/"below"/"left-far"}] | link{from,to,label} 两点虚线(竖线时标签竖排)、polarity{up,down} 右侧正负箭头、ring{point,label,color} 虚线圈 |
slot 老虎机 | title reels:[4 个名字] captions:[停下后每列说明] bet idle | spin{result:["✓","✗","?","✓"],value:"Y = +95",color} |
card 变量卡 | mark:"✓"/"✗"/"?" title tag tagColor index:"1 / 4",body 见下 | – |
network 关系网 | – | strong{label,note} 黄色强纽带、weak{label,pulse} 青色弱纽带 + 信息流、info{title,rows:[[k,v]]} |
triangle 三元闭包 | a b 两端名字 | link A–B 连线、break 断开 B 变红、addC{label,inner} 出现 C 和金色三角、note{side:"left"/"right"/"bottom",text} |
bigtext 点阵结尾 | line1 line2 color people(5) | – |
card.body:
{type:"waves", rows:[{a,b,match:true/false,label,at}]}:两人之间的波形,同频/不同频{type:"split", cols:[{title,sub:[..],people,boxes,note,meter,meterColor,at}]}:左右两种状态对比{type:"beats", rows:[{label,count,color,at}], verdict:"不合拍", verdictAt}:节奏条对比{type:"quotes", quotes:[{text,x,y,at}], meter:"接收阈值", meterAt}:两句心声(主角约 x=360,对方约 x=1360)+ 阈值条充满后出现护盾yellow red cyan green purple 或 #hex;字幕标记只有 y/r/c/g。preview.jpg(每场景 2 帧),发现问题改 spec 或 engine,不要直接全量渲染试错。engine.html 里加一个 sceneXxx(sc, lt) 并注册到 SCENES,按第 3 节像素纯度标准写,同步更新本文件表格和三处存档(用户电脑 / Project / GitHub)。audio\line_XXX.mp3 重新双击 配音.bat(已存在的会跳过)。© ChenShuo2004, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (assets) in cs-pixel-explainer of ChenShuo2004/cs-skills.
Open the folder on GitHubat commit 6f5009d
Cs Pixel Explainer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cs Pixel Explainer this skillChenShuo2004/cs-skills | 193 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Storyreceptron/mulmocast-cli | 476 | — | ~3.5k | Automated safety check: Notes | None | |
| Render Value Propgooseworks-ai/goose-skills | 1.2k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Explain Videolimin112/min-skill | 362 | — | ~2.4k | Automated safety check: Pass | None | |
| Whiteboard Videotrustfuture/simon-skills | 353 | — | ~1.8k | Automated safety check: Notes | MIT | |
| Immersive Short Videoxrkseek/XRK-AGT | 140 | — | ~1k | Automated safety check: Pass | MIT |
receptron/mulmocast-cli
Create high-quality MulmoScript through structured multi-phase creative process
gooseworks-ai/goose-skills
Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook…
limin112/min-skill
Build a narrated explainer video from a concept — discussion → structure → HTML slide deck → narration script → TTS voice → subtitles → background music → Playwright screen recording → ffmpeg…
trustfuture/simon-skills
手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实…
xrkseek/XRK-AGT
Produce immersive vertical short videos (口播/科普/产品讲解) without AI-slop aesthetics.
fabricioctelles/skills
Produce a short motion-graphics video ad — a 15s Facebook/Instagram/TikTok spot — as a rendered MP4.
ChenShuo2004/cs-skills
A skill your agent uses when the user asks to save the current repository version, create a rollback point, checkpoint dirty worktree changes, preserve staged/unstaged/untracked files before risky…
ChenShuo2004/cs-skills
用代码做动画视频:页面暴露 render(t),Playwright 逐帧截图 + FFmpeg 合成 mp4,可接合成配乐、出图和配音。通用模式先明确主题、规格、风格和声音,出风格卡、分镜与关键帧后逐镜制作;Vibe知识大赏模式额外查证来源、记录真实素材许可、先渲 10 秒样片。触发词包括…
ChenShuo2004/cs-skills
制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。
ChenShuo2004/cs-skills
A skill your agent uses when the user types $cs-auto-videl or asks for Douyin/TikTok ecommerce video workflows, including competitor replication, strong-Hook nine-grid promptimage.md to image2…
ChenShuo2004/cs-skills
当用户要把产品事实、口播、数字人、产品界面和 CTA 制作成可验收的数字人产品介绍视频时使用:统一预检 ChatCut、FFmpeg、ComfyUI、Fish/TTS 与 Remotion,按 plan、sample、batch 三种模式编排,先完成可审批样片再批量或出成片。用于有明确产品包的横版/竖版产品视频流水线;不要用于通用自动剪辑、电商短视频复刻、纯视频选题策划或未经确认的批量生成与发布。
ChenShuo2004/cs-skills
把中文口播、角色和参考素材制作成可验收的 16:9 代码叙事视频:A-roll 角色讲述、全屏场景 B-roll、真实音频时码、Remotion 样片与成片、3:4/4:3 杂志风封面。仅用于代码驱动的叙事视频,不替代 ChatCut 剪辑、数字人产品片或电商复刻。
Works with
Categories
把中文口播文案做成像素风 + 坐标系隐喻 + 打字机字幕的动画解说视频(含 edge-tts 配音):先问 5 项输入、写分镜表与 3 张关键帧等确认,再写 spec.json、配音、逐帧渲染 1080p mp4。用户给文案并要像素风 / 注意力赌博那种风格、或确认是像素解说系列续集时使用;独立单片和其他风格走 $cs-code-video,暗夜星空知识片走 $cs-knowledge-film。. Cs Pixel Explainer is an agent skill from ChenShuo2004/cs-skills.
Cs Pixel Explainer fits situations like: tasks that involve Text to speech and voice.
Run `npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a claude-code`. Or copy the skill folder (cs-pixel-explainer in ChenShuo2004/cs-skills) into .claude/skills/cs-pixel-explainer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a codex`. Or copy the skill folder (cs-pixel-explainer in ChenShuo2004/cs-skills) into .agents/skills/cs-pixel-explainer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ChenShuo2004/cs-skills --skill cs-pixel-explainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cs-pixel-explainer, .gemini/skills/cs-pixel-explainer, .github/skills/cs-pixel-explainer and .opencode/skills/cs-pixel-explainer in your project.
Going by SKILL.md and its folder, Cs Pixel Explainer needs JavaScript, Python and Windows cmd for the scripts in its folder and the command-line tools its instructions call (node, python, git and python3). Our summary lists: Python 3; Node.js.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cs Pixel Explainer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Cs Pixel Explainer: Story (receptron/mulmocast-cli, 476 stars), Render Value Prop (gooseworks-ai/goose-skills, 1.2k stars), Explain Video (limin112/min-skill, 362 stars) and Whiteboard Video (trustfuture/simon-skills, 353 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ChenShuo2004 (a GitHub user) maintains it in ChenShuo2004/cs-skills, which has 193 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 8, 2026.
Source: ChenShuo2004/cs-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.